Artificial Intelligence & Ethics

Global: New Black‑Box Jailbreak Method Boosts LLM Attack EfficiencyResearchers have introduced a black‑box technique called Jailbreak with Cross‑Behavior attacks (JCB) to improve the efficiency of prompting large language models (LLMs)…

Global: Neuroscience-Inspired Neural Networks Enable Targeted Machine UnlearningResearchers who authored a recent arXiv preprint (arXiv:2410.22374v2, posted October 2024) introduced a novel approach that allows machine‑learning models to selectively forget portions…

Global: Researchers Advocate Brain-Inspired Enhancements for Safer, Interpretable AIA team of researchers posted a new preprint on arXiv in December 2025 proposing that next‑generation foundation models incorporate three brain‑inspired components—action…

Global: AI Framework Cuts Bias in Bangladesh Flood Aid AllocationOverviewA fairness‑aware artificial intelligence framework designed to prioritize post‑flood aid distribution in Bangladesh has demonstrated significant reductions in allocation bias while…

Global: New Framework Aims to Guide Governance of Agentic AI SystemsA team of researchers associated with GovTech Responsible AI has introduced the Agentic Risk & Capability (ARC) Framework, a technical…

Global: Logic Sketch Prompting Improves Accuracy and Consistency Across Leading Open-Weight LLMsResearchers who posted a new preprint on arXiv in December 2025 introduced a lightweight prompting framework called Logic Sketch…

Global: Detecting Hidden Conversational Escalation in AI ChatbotsResearchers Jihyung Park, Saleh Afroogh, and Junfeng Jiao announced on December 5, 2025, that they have developed a novel system for identifying covert…

Global: Study Introduces Emotion-Inspired Signals to Boost AI AutonomyA team of researchers announced a new framework on arXiv that aims to enhance the robustness of artificial intelligence agents by incorporating…

Global: New Framework SoliReward Improves Video Generation Reward ModelingA team of AI researchers has introduced a systematic framework called SoliReward to enhance post‑training alignment of video generation models with human…

Global: Researchers Develop Tailored Backdoor Attack Framework for Prompt-Driven Video Segmentation ModelsA new study posted to arXiv reveals that a team of researchers has designed a specialized backdoor attack method,…